@inproceedings{le-etal-2019-multimodal,
    title = "Multimodal Transformer Networks for End-to-End Video-Grounded Dialogue Systems",
    author = "Le, Hung  and
      Sahoo, Doyen  and
      Chen, Nancy  and
      Hoi, Steven",
    editor = "Korhonen, Anna  and
      Traum, David  and
      M{\`a}rquez, Llu{\'i}s",
    booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
    month = jul,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/P19-1564/",
    doi = "10.18653/v1/P19-1564",
    pages = "5612--5623"
}